Dynamic-TreeRPO: Breaking the Independent Trajectory Bottleneck with Structured Sampling

• URL: http://arxiv.org/abs/2509.23352v2
• Date: Wed, 01 Oct 2025 04:11:51 GMT
• Title: Dynamic-TreeRPO: Breaking the Independent Trajectory Bottleneck with Structured Sampling
• Authors: Xiaolong Fu, Lichen Ma, Zipeng Guo, Gaojing Zhou, Chongxiao Wang, ShiPing Dong, Shizhe Zhou, Shizhe Zhou, Ximan Liu, Jingling Fu, Tan Lit Sin, Yu Shi, Zhen Chen, Junshi Huang, Jason Li,
• Abstract summary: We propose Dynamic-TreeRPO, which implements the sliding-window sampling strategy as a tree-structured noise intensities along depth.<n>With well-designed noise intensities for each tree layer, Dynamic-TreeRPO can enhance the variation of exploration without any extra computational cost.
• Score: 14.415169190908676
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The integration of Reinforcement Learning (RL) into flow matching models for text-to-image (T2I) generation has driven substantial advances in generation quality. However, these gains often come at the cost of exhaustive exploration and inefficient sampling strategies due to slight variation in the sampling group. Building on this insight, we propose Dynamic-TreeRPO, which implements the sliding-window sampling strategy as a tree-structured search with dynamic noise intensities along depth. We perform GRPO-guided optimization and constrained Stochastic Differential Equation (SDE) sampling within this tree structure. By sharing prefix paths of the tree, our design effectively amortizes the computational overhead of trajectory search. With well-designed noise intensities for each tree layer, Dynamic-TreeRPO can enhance the variation of exploration without any extra computational cost. Furthermore, we seamlessly integrate Supervised Fine-Tuning (SFT) and RL paradigm within Dynamic-TreeRPO to construct our proposed LayerTuning-RL, reformulating the loss function of SFT as a dynamically weighted Progress Reward Model (PRM) rather than a separate pretraining method. By associating this weighted PRM with dynamic-adaptive clipping bounds, the disruption of exploration process in Dynamic-TreeRPO is avoided. Benefiting from the tree-structured sampling and the LayerTuning-RL paradigm, our model dynamically explores a diverse search space along effective directions. Compared to existing baselines, our approach demonstrates significant superiority in terms of semantic consistency, visual fidelity, and human preference alignment on established benchmarks, including HPS-v2.1, PickScore, and ImageReward. In particular, our model outperforms SoTA by $4.9\%$, $5.91\%$, and $8.66\%$ on those benchmarks, respectively, while improving the training efficiency by nearly $50\%$.

Related papers

• TopoCurate:Modeling Interaction Topology for Tool-Use Agent Training [53.93696896939915]
  Training tool-use agents typically rely on Supervised Fine-Tuning (SFT) on successful trajectories and Reinforcement Learning (RL) on pass-rate-selected tasks.<n>We propose TopoCurate, an interaction-aware framework that projects multi-trial rollouts from the same task into a unified semantic quotient topology.<n>TopoCurate achieves consistent gains of 4.2% (SFT) and 6.9% (RL) over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-03-02T10:38:54Z)
• WorldTree: Towards 4D Dynamic Worlds from Monocular Video using Tree-Chains [13.122536259577453]
  WorldTree is a unified framework that enables coarse-to-fine optimization based on inheritance-based partition tree structure for hierarchical temporal decomposition.<n>Our proposed method achieves 8.26% improvement of LPIPS on NVIDIA-LS and 9.09% improvement of reconstruction on DyCheck compared to the second-best method.
  arXiv  Detail & Related papers  (2026-02-12T11:38:35Z)
• TIDE: Tuning-Integrated Dynamic Evolution for LLM-Based Automated Heuristic Design [7.264986493460248]
  TIDE is a Tuning-Integrated Dynamic Evolution framework designed to decouple structural reasoning from parameter optimization.<n> experiments across nine optimization problems demonstrate that TIDE significantly outperforms state-of-the-art tuning methods.
  arXiv  Detail & Related papers  (2026-01-29T04:00:02Z)
• TreePS-RAG: Tree-based Process Supervision for Reinforcement Learning in Agentic RAG [71.06073770344732]
  Agentic retrieval-augmented generation (RAG) formulates question answering as a multi-step interaction between reasoning and information retrieval.<n>We present TreePS-RAG, an online, tree-based RL framework for agentic RAG that enables step-wise credit assignment while retaining outcome-only rewards.
  arXiv  Detail & Related papers  (2026-01-11T14:07:30Z)
• TreeGRPO: Tree-Advantage GRPO for Online RL Post-Training of Diffusion Models [14.130608036489336]
  Reinforcement learning (RL) post-training is crucial for aligning generative models with human preferences, but its prohibitive computational cost remains a major barrier to widespread adoption.<n>We introduce textbfTreeGRPO, a novel RL framework that dramatically improves training efficiency by recasting the denoising process as a search tree.
  arXiv  Detail & Related papers  (2025-12-09T01:17:34Z)
• Tree Search for LLM Agent Reinforcement Learning [23.7084695563981]
  Tree-based Group Relative Policy Optimization (Tree-GRPO) is a grouped agent RL method based on tree search.<n>By sharing common prefixes, the tree search sampling increases the number of rollouts achievable.<n>We demonstrate that the objective of intra-tree level group relative policy optimization is equivalent to that of step-level direct preference learning.
  arXiv  Detail & Related papers  (2025-09-25T14:37:09Z)
• TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling [65.46347858249295]
  TreePO is a self-guided rollout algorithm that views sequence generation as a tree-structured searching process.<n>TreePO essentially reduces the per-update compute burden while preserving or enhancing exploration diversity.
  arXiv  Detail & Related papers  (2025-08-24T16:52:37Z)
• TreeLoRA: Efficient Continual Learning via Layer-Wise LoRAs Guided by a Hierarchical Gradient-Similarity Tree [52.44403214958304]
  In this paper, we introduce TreeLoRA, a novel approach that constructs layer-wise adapters by leveraging hierarchical gradient similarity.<n>To reduce the computational burden of task similarity estimation, we employ bandit techniques to develop an algorithm based on lower confidence bounds.<n> experiments on both vision transformers (ViTs) and large language models (LLMs) demonstrate the effectiveness and efficiency of our approach.
  arXiv  Detail & Related papers  (2025-06-12T05:25:35Z)
• Flow-GRPO: Training Flow Matching Models via Online RL [75.70017261794422]
  We propose Flow-GRPO, the first method integrating online reinforcement learning (RL) into flow matching models.<n>Our approach uses two key strategies: (1) an ODE-to-SDE conversion that transforms a deterministic Ordinary Equation (ODE) into an equivalent Differential Equation (SDE) that matches the original model's marginal distribution at all timesteps; and (2) a Denoising Reduction strategy that reduces training denoising steps while retaining the original inference timestep number.
  arXiv  Detail & Related papers  (2025-05-08T17:58:45Z)
• Heterogeneous Learning Rate Scheduling for Neural Architecture Search on Long-Tailed Datasets [0.0]
  We propose a novel adaptive learning rate scheduling strategy tailored for the architecture parameters of DARTS. Our approach dynamically adjusts the learning rate of the architecture parameters based on the training epoch, preventing the disruption of well-trained representations.
  arXiv  Detail & Related papers  (2024-06-11T07:32:25Z)
• REBEL: Reinforcement Learning via Regressing Relative Rewards [59.68420022466047]
  We propose REBEL, a minimalist RL algorithm for the era of generative models.<n>In theory, we prove that fundamental RL algorithms like Natural Policy Gradient can be seen as variants of REBEL.<n>We find that REBEL provides a unified approach to language modeling and image generation with stronger or similar performance as PPO and DPO.
  arXiv  Detail & Related papers  (2024-04-25T17:20:45Z)
• Dynamic PlenOctree for Adaptive Sampling Refinement in Explicit NeRF [6.135925201075925]
  We propose the dynamic PlenOctree DOT, which adaptively refines the sample distribution to adjust to changing scene complexity. Compared with POT, our DOT outperforms it by enhancing visual quality, reducing over $55.15$/$68.84%$ parameters, and providing 1.7/1.9 times FPS for NeRF-synthetic and Tanks $&$ Temples, respectively.
  arXiv  Detail & Related papers  (2023-07-28T06:21:42Z)
• Latent Variable Representation for Reinforcement Learning [131.03944557979725]
  It remains unclear theoretically and empirically how latent variable models may facilitate learning, planning, and exploration to improve the sample efficiency of model-based reinforcement learning. We provide a representation view of the latent variable models for state-action value functions, which allows both tractable variational learning algorithm and effective implementation of the optimism/pessimism principle. In particular, we propose a computationally efficient planning algorithm with UCB exploration by incorporating kernel embeddings of latent variable models.
  arXiv  Detail & Related papers  (2022-12-17T00:26:31Z)
• DessiLBI: Exploring Structural Sparsity of Deep Networks via Differential Inclusion Paths [45.947140164621096]
  We propose a new approach based on differential inclusions of inverse scale spaces. We show that DessiLBI unveils "winning tickets" in early epochs.
  arXiv  Detail & Related papers  (2020-07-04T04:40:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.